{"total":56,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2505.16282","title":"ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay","created":"2025-05-22","cited_by_count":77,"area":"agents"},{"id":"2505.20732","title":"SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution","created":"2025-05-27","cited_by_count":73,"area":"agents"},{"id":"2506.01716","title":"Self-Challenging Language Model Agents","created":"2025-06-02","cited_by_count":59,"area":"agents"},{"id":"2504.16129","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning","created":"2025-04-21","cited_by_count":52,"area":"agents"},{"id":"2511.02208","title":"Training Proactive and Personalized LLM Agents","created":"2025-11-04","cited_by_count":46,"area":"agents"},{"id":"2504.11543","title":"REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites","created":"2025-04-15","cited_by_count":45,"area":"agents"},{"id":"2511.12159","title":"CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic","created":"2025-11-15","cited_by_count":30,"area":"agents"},{"id":"2511.14460","title":"Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning","created":"2025-11-18","cited_by_count":29,"area":"agents"},{"id":"2510.20022","title":"SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph","created":"2025-10-22","cited_by_count":28,"area":"agents"},{"id":"2505.17716","title":"Get Experience from Practice: LLM Agents with Record & Replay","created":"2025-05-23","cited_by_count":23,"area":"agents"},{"id":"2507.04103","title":"How to Train Your LLM Web Agent: A Statistical Diagnosis","created":"2025-07-05","cited_by_count":19,"area":"agents"},{"id":"2603.26233","title":"Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents","created":"2026-03-27","cited_by_count":19,"area":"agents"},{"id":"2510.01132","title":"A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning","created":"2025-10-01","cited_by_count":17,"area":"agents"},{"id":"2511.02687","title":"The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation","created":"2025-11-04","cited_by_count":13,"area":"agents"},{"id":"2602.21534","title":"ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning","created":"2026-02-25","cited_by_count":13,"area":"agents"},{"id":"2505.17767","title":"Position: The Real Barrier to LLM Agent Usability is Agentic ROI","created":"2025-05-23","cited_by_count":12,"area":"agents"},{"id":"2605.20204","title":"RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation","created":"2026-04-07","cited_by_count":12,"area":"agents"},{"id":"2507.11633","title":"General Modular Harness for LLM Agents in Multi-Turn Gaming Environments","created":"2025-07-15","cited_by_count":11,"area":"agents"},{"id":"2508.04037","title":"Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agent","created":"2025-08-06","cited_by_count":11,"area":"agents"},{"id":"2510.08240","title":"The Alignment Waltz: Jointly Training Agents to Collaborate for Safety","created":"2025-10-09","cited_by_count":10,"area":"agents"},{"id":"2605.12894","title":"Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents","created":"2026-05-13","cited_by_count":10,"area":"agents"},{"id":"2506.00539","title":"ARIA: Training Language Agents with Intention-Driven Reward Aggregation","created":"2025-05-31","cited_by_count":9,"area":"agents"},{"id":"2510.11035","title":"SusBench: An Online Benchmark for Evaluating Dark Pattern Susceptibility of Computer-Use Agents","created":"2025-10-13","cited_by_count":8,"area":"agents"},{"id":"2511.11828","title":"Conformal Constrained Policy Optimization for Cost-Effective LLM Agents","created":"2025-11-14","cited_by_count":7,"area":"agents"},{"id":"2602.11767","title":"TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents","created":"2026-02-12","cited_by_count":7,"area":"agents"},{"id":"2604.08567","title":"Multi-User Large Language Model Agents","created":"2026-03-19","cited_by_count":7,"area":"agents"},{"id":"2601.18217","title":"Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents","created":"2026-01-26","cited_by_count":6,"area":"agents"},{"id":"2604.07960","title":"TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning","created":"2026-04-09","cited_by_count":6,"area":"agents"},{"id":"2608.12253","title":"One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL","created":"2026-08-12","cited_by_count":6,"area":"agents"},{"id":"2511.00413","title":"Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse","created":"2025-11-01","cited_by_count":5,"area":"agents"},{"id":"2607.20536","title":"AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2602.05327","title":"ProAct: Agentic Lookahead in Interactive Environments","created":"2026-02-05","cited_by_count":3,"area":"agents"},{"id":"2604.07645","title":"PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent","created":"2026-04-08","cited_by_count":3,"area":"agents"},{"id":"2604.27955","title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","created":"2026-04-30","cited_by_count":3,"area":"agents"},{"id":"2605.10674","title":"Step Rejection Fine-Tuning: A Practical Distillation Recipe","created":"2026-05-11","cited_by_count":3,"area":"agents"},{"id":"2608.12355","title":"Humans are Missing from AI Coding Agent Research","created":"2026-07-04","cited_by_count":3,"area":"agents"},{"id":"2604.10182","title":"Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision","created":"2026-04-11","cited_by_count":2,"area":"agents"},{"id":"2608.22152","title":"The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate","created":"2026-08-23","cited_by_count":2,"area":"agents"},{"id":"2609.19801","title":"DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum","created":"2026-09-17","cited_by_count":2,"area":"agents"},{"id":"2603.07927","title":"SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2608.24588","title":"IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2608.27818","title":"AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics","created":"2026-08-28","cited_by_count":1,"area":"agents"},{"id":"2609.02417","title":"Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment","created":"2026-09-02","cited_by_count":1,"area":"agents"},{"id":"2510.17173","title":"Offline Policy Evaluation of Multi-Turn LLM Health Coaching with Real Users","created":"2025-10-20","cited_by_count":0,"area":"agents"},{"id":"2605.07011","title":"Dual-Agent Co-Training for Health Coaching via Implicit Adversarial Preference Optimization","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2607.25369","title":"ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.03166","title":"Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2609.29051","title":"From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2610.15840","title":"LLM Value Functions for Credit Assignment in Agentic RL","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.16155","title":"Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.16523","title":"EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17757","title":"Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.18868","title":"Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19103","title":"Contextual Credit Policy Optimization","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}